Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2073 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.7148. Min Act: -0.0000

Data Index: 593968 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.6242. Min Act: -0.0000

Data Index: 77973 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4630. Min Act: -0.0000

Data Index: 282883 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.5856. Min Act: -0.0000

Data Index: 1347782 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4604. Min Act: -0.0000

Data Index: 996460 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4716. Min Act: -0.0000

Data Index: 155708 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4631. Min Act: -0.0000

Data Index: 600050 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.3215. Min Act: -0.0000

Data Index: 632989 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.3408. Min Act: -0.0000

Data Index: 665093 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.4008. Min Act: -0.0000

Data Index: 1204382 (The Pile)

Max Activating Token Index: 686

Text #10

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.3187. Min Act: -0.0000

Data Index: 1627531 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1548942 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.3046. Min Act: -0.0000

Data Index: 932160 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.2958. Min Act: -0.0000

Data Index: 185702 (The Pile)

Max Activating Token Index: 355

Text #14

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1690600 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.3046. Min Act: -0.0000

Data Index: 1957512 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.3685. Min Act: -0.0000

Data Index: 645500 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.2660. Min Act: -0.0000

Data Index: 746385 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.2670. Min Act: -0.0000

Data Index: 210394 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 1.7148. Min Range: -1.7148

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1649009 (The Pile)

Max Activating Token Index: 686